๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Optimal Average Value Convergence in Nonhomogeneous Markov Decision Processes

โœ Scribed by Y.S. Park; J.C. Bean; R.L. Smith


Publisher
Elsevier Science
Year
1993
Tongue
English
Weight
430 KB
Volume
179
Category
Article
ISSN
0022-247X

No coin nor oath required. For personal study only.


๐Ÿ“œ SIMILAR VOLUMES


A New Class of Policies in Vector-Valued
โœ Kazuyoshi Wakuta ๐Ÿ“‚ Article ๐Ÿ“… 1996 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 108 KB

For a vector-valued Markov decision process with discounted reward criterion, we introduce a new class of policies called the semi-stationary policies and show that an optimal semi-stationary policy that attains the extreme points of the set of rewards induced by all policies can be described as a c